RE: st: odds ratio vs. RRR in multinomial logistic regression
Wed, 10 Aug 2005 21:04:30 +0100
I don't think this could be much plainer. It
could be tinkered with as a matter of style,
but that seems a different issue. Some readers
prefer percents, so you could consider variations
given X, the relative risk of outcome 3 is 85% that of
> Some of the statalist members were kind enough to
> respond to my inquiry a few months ago about
> interpreting multinomial logistic regression and the
> resulting RRR.
> I received this response about reporting the results:
> "For the RRR it would be, for example, 'the relative
> risk of outcome 3 associated with X is 0.85 times
> the relative risk of outcome 1 associated with X'."
> This was helpful, but when I wrote it up in my
> dissertation this way, my advisor has told me that I
> need to put it in "plain English." Can anyone help me
> put this sentence into more interpretable language for
> someone who is not very familiar with RRR?
> I had already written up a detailed description of
> where the RRR comes from and then followed it with the
> results reported as above, but my advisor is still
> requiring a more intuitive or interpretable sentence.
* For searches and help try: